Writing

Notes with numbers in them.

Long-form write-ups of benchmarks and reproductions, published when there's something real to show. No posting schedule; depth over cadence.

Peer-reviewed · 2025

Real-time yoga pose estimation with a hybrid MoveNet architecture

My first-author paper: a Thunder-train, Lightning-infer MoveNet split that classifies 11 yoga asanas at 99% accuracy while holding 30+ FPS on consumer hardware. Published in Sādhanā (Indian Academy of Sciences, Springer).

July 2026

Buying nothing: scoring a decade of ownership deception in Terms of Service

DODI is a deterministic 0–100 index of how hard a platform's ToS works to hide that "Buy now" means "revocable licence". Ten platforms, four Wayback snapshots each from 2015 to 2024: the language got worse, GOG scores best exactly as it should, and Netflix's licence-to-ownership ratio hit 49.5.

Python · textstat · SciPy · ToS;DR validation · Wayback Machine corpus
July 2026

Benchmarking Arabic OCR and translation on an 8 GB laptop GPU

What Surya and PaddleOCR actually do on KITAB-Bench, how Opus-MT stacks up against NLLB-1.3B on Arabic→German, why the best translator scored the worst BLEU, the failure modes that only show up on long legal text and how a triage pipeline learns to distrust itself.

Surya OCR · PaddleOCR · Opus-MT · NLLB · CER/WER · confidence calibration